CtrlK
BlogDocsLog inGet started
Tessl Logo

announcing-behavior-changes

Decides whether a behavior-changing fix needs an in-app notice, then builds one that reaches only the affected users and can be removed later. Use when a change alters what an existing user sees without them doing anything — a metric moves, a chart shifts, a count drops, a date range resolves differently, a matcher matches differently — and when adding, reviewing, or removing such a notice. Trigger terms: behavior change, breaking change, semantics change, "results may differ", change notice, deprecation banner, migration banner. Carries the gate (narrow to the affected users with a tested predicate, or do not ship a notice at all), the pattern from `SqlInsightDateFilterNotice`, where to anchor the notice, and the flag-based removal path. Not for new features (use the changelog), not for permanent per-object warnings computed by the backend, and not for the wording itself (see `/writing-user-facing-copy`).

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured, actionable, and sequence-clear with concrete code, paths, and a checklist, plus an honest account of the unautomated removal gap. The only modest slack is in conciseness and a couple of workflow checkpoints.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's TS/React/feature-flag knowledge; each explanatory sentence (dismissKey reasoning, the stale-removal gap) earns its place, with only minor instances that could be trimmed, so it sits above 3 but short of the fully-lean 5 anchor.

4 / 5

Actionability

Provides concrete, copy-paste-ready TS/TSX (predicate signature, flag constant, full component), exact file paths, a copy example, and a named test model, covering the common cases fully executably.

5 / 5

Workflow Clarity

Clear sequence — the four-gate narrowing test, the five-piece pattern, and a checklist — with an explicit testing/validation checkpoint (predicate tested both ways) and an honest removal workflow; minor gaps keep it just below the explicit feedback-loop 5 anchor.

4 / 5

Progressive Disclosure

No bundle files exist; the single ~130-line body is well-organized into clear sections and cross-skill references (/writing-user-facing-copy, /cleaning-up-stale-feature-flags, /writing-tests) are one level deep and clearly signaled, meeting the simple-skills well-organized exception.

5 / 5

Total

18

/

20

Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is precise, trigger-rich, and complete, clearly stating what the skill does and when to use it with concrete natural-language triggers and explicit non-goals. Minor specificity gap only in that actions are described in prose rather than enumerated.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Decides whether... needs an in-app notice, then builds one that reaches only the affected users and can be removed later') but does not enumerate a full list of discrete actions, so it sits below the 5 anchor and above 3.

4 / 5

Completeness

Explicitly answers both what ('Decides whether... builds one...') and when ('Use when...'), with concrete trigger phrases plus a 'Not for...' boundary clause.

5 / 5

Trigger Term Quality

Provides a dedicated 'Trigger terms:' line with comprehensive natural phrases and synonyms (behavior change, breaking change, 'results may differ', deprecation banner, migration banner), matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear narrow niche (in-app notices for behavior-changing fixes) with distinct trigger terms and an explicit 'Not for...' list that fences off adjacent skills, minimizing conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
PostHog/posthog
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.